Tootfinder

ChatGPT on the Road: Leveraging Large Language Model-Powered In-vehicle Conversational Agents for Safer and More Enjoyable Driving Experience
Yeana Lee Bond (Computer Science, Virginia Tech, Blacksburg, Virginia, USA), Mungyeong Choe (Industrial and Systems Engineering, Virginia Tech, Blacksburg, Virginia, USA), Baker Kasim Hasan (Computer Science, Virginia Tech, Blacksburg, Virginia, USA), Arsh Siddiqui (Computer Science, Virginia Tech, Blacksburg, Virginia, USA), Myounghoon Jeon (Com…

ChatGPT on the Road: Leveraging Large Language Model-Powered In-vehicle Conversational Agents for Safer and More Enjoyable Driving Experience
Studies on in-vehicle conversational agents have traditionally relied on pre-scripted prompts or limited voice commands, constraining natural driver-agent interaction. To resolve this issue, the present study explored the potential of a ChatGPT-based in-vehicle agent capable of carrying continuous, multi-turn dialogues. Forty drivers participated in our experiment using a motion-based driving simulator, comparing three conditions (No agent, Pre-scripted agent, and ChatGPT-based agent) as a with…

Exploring Large Language Model Agents for Piloting Social Experiments
Jinghua Piao, Yuwei Yan, Nian Li, Jun Zhang, Yong Li
https://arxiv.org/abs/2508.08678 https://

Exploring Large Language Model Agents for Piloting Social Experiments
Computational social experiments, which typically employ agent-based modeling to create testbeds for piloting social experiments, not only provide a computational solution to the major challenges faced by traditional experimental methods, but have also gained widespread attention in various research fields. Despite their significance, their broader impact is largely limited by the underdeveloped intelligence of their core component, i.e., agents. To address this limitation, we develop a framewo…

Multi-agent systems for chemical engineering: A review and perspective
Sophia Rupprecht, Qinghe Gao, Tanuj Karia, Artur M. Schweidtmann
https://arxiv.org/abs/2508.07880 https://…

Multi-agent systems for chemical engineering: A review and perspective
Large language model (LLM)-based multi-agent systems (MASs) are a recent but rapidly evolving technology with the potential to transform chemical engineering by decomposing complex workflows into teams of collaborative agents with specialized knowledge and tools. This review surveys the state-of-the-art of MAS within chemical engineering. While early studies demonstrate promising results, scientific challenges remain, including the design of tailored architectures, integration of heterogeneous …

KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows
Zaifeng Pan, Ajjkumar Patel, Zhengding Hu, Yipeng Shen, Yue Guan, Wan-Lu Li, Lianhui Qin, Yida Wang, Yufei Ding
https://arxiv.org/abs/2507.07400

KVFlow: Efficient Prefix Caching for Accelerating LLM-Based Multi-Agent Workflows
Large language model (LLM) based agentic workflows have become a popular paradigm for coordinating multiple specialized agents to solve complex tasks. To improve serving efficiency, existing LLM systems employ prefix caching to reuse key-value (KV) tensors corresponding to agents' fixed prompts, thereby avoiding redundant computation across repeated invocations. However, current systems typically evict KV caches using a Least Recently Used (LRU) policy, which fails to anticipate future agent us…

CancerGUIDE: Cancer Guideline Understanding via Internal Disagreement Estimation
Alyssa Unell, Noel C. F. Codella, Sam Preston, Peniel Argaw, Wen-wai Yim, Zelalem Gero, Cliff Wong, Rajesh Jena, Eric Horvitz, Amanda K. Hall, Ruican Rachel Zhong, Jiachen Li, Shrey Jain, Mu Wei, Matthew Lungren, Hoifung Poon
https://arxiv.org/abs/2509.07325…

CancerGUIDE: Cancer Guideline Understanding via Internal Disagreement Estimation
The National Comprehensive Cancer Network (NCCN) provides evidence-based guidelines for cancer treatment. Translating complex patient presentations into guideline-compliant treatment recommendations is time-intensive, requires specialized expertise, and is prone to error. Advances in large language model (LLM) capabilities promise to reduce the time required to generate treatment recommendations and improve accuracy. We present an LLM agent-based approach to automatically generate guideline-con…

The Dark Side of LLMs Agent-based Attacks for Complete Computer Takeover
Matteo Lupinacci, Francesco Aurelio Pironti, Francesco Blefari, Francesco Romeo, Luigi Arena, Angelo Furfaro
https://arxiv.org/abs/2507.06850

The Dark Side of LLMs Agent-based Attacks for Complete Computer Takeover
The rapid adoption of Large Language Model (LLM) agents and multi-agent systems enables unprecedented capabilities in natural language processing and generation. However, these systems have introduced unprecedented security vulnerabilities that extend beyond traditional prompt injection attacks. This paper presents the first comprehensive evaluation of LLM agents as attack vectors capable of achieving complete computer takeover through the exploitation of trust boundaries within agentic AI syst…

Emergence of Cooperation and Commitment in Optional Prisoner's Dilemma
Zhao Song, The Anh Han
https://arxiv.org/abs/2508.06702 https://arxiv.org/pdf/25…

Emergence of Cooperation and Commitment in Optional Prisoner's Dilemma
Commitment is a well-established mechanism for fostering cooperation in human society and multi-agent systems. However, existing research has predominantly focused on the commitment that neglects the freedom of players to abstain from an interaction, limiting their applicability to many real-world scenarios where participation is often voluntary. In this paper, we present a two-stage game model to investigate the evolution of commitment-based behaviours and cooperation within the framework of t…

Decentralized Local Voltage Control for Active Distribution Networks
Diana Vieira Fernandes, Soummya Kar, Carlos Santos Silva
https://arxiv.org/abs/2509.09048 https://

Decentralized Local Voltage Control for Active Distribution Networks
Distribution networks face challenges from the increasing deployment of Distributed Energy Resources (DERs) and the emergence of bidirectional power flows. We propose a decentralized Volt/VAr control method based on a saddle-point reformulation and consensus+innovation (C+I) updates. Each agent at a controllable bus computes and enforces its own set-points using only neighbor communication. Our method embeds passive buses directly, preserves network physics through a linearized Jacobian model, …

Simulation of a generalized asset exchange model with investment and income mechanisms
Jan Tobochnik, Harvey Gould, William Klein
https://arxiv.org/abs/2508.05810 https://

Simulation of a generalized asset exchange model with investment and income mechanisms
An agent-based model of the economy is generalized to incorporate investment and guaranteed income mechanisms in addition to the exchange and distribution mechanisms considered in earlier models. We find realistic wealth distributions and realistic values of the Gini coefficients and the Pareto index. We also show that although the system reaches a steady state, the system is not in thermal equilibrium. The nonequilibrium behavior is associated with the multiplicative noise generated by the inv…

Large Language Model-based Data Science Agent: A Survey
Peiran Wang, Yaoning Yu, Ke Chen, Xianyang Zhan, Haohan Wang
https://arxiv.org/abs/2508.02744 https://

Large Language Model-based Data Science Agent: A Survey
The rapid advancement of Large Language Models (LLMs) has driven novel applications across diverse domains, with LLM-based agents emerging as a crucial area of exploration. This survey presents a comprehensive analysis of LLM-based agents designed for data science tasks, summarizing insights from recent studies. From the agent perspective, we discuss the key design principles, covering agent roles, execution, knowledge, and reflection methods. From the data science perspective, we identify key …

When Heterogeneity Drives Hysteresis: Anticonformity in the Multistate q-Voter Model on Networks
Arkadiusz Lipiecki, Katarzyna Sznajd-Weron
https://arxiv.org/abs/2509.07944 http…

When Heterogeneity Drives Hysteresis: Anticonformity in the Multistate q-Voter Model on Networks
Discontinuous phase transitions are closely linked to tipping points, critical mass effects, and hysteresis, phenomena that have been confirmed empirically and recognized as highly important in social systems. The multistate $q$-voter model, an agent-based approach to simulate discrete decision-making and opinion dynamics, is particularly relevant in this context. Previous studies of the $q$-voter model with anticonformity on complete graphs uncovered a counterintuitive result. Changing the mod…

Incentives for Digital Twins: Task-Based Productivity Enhancements with Generative AI
Catherine Wu, Arun Sundararajan
https://arxiv.org/abs/2509.08732 https://

Incentives for Digital Twins: Task-Based Productivity Enhancements with Generative AI
Generative AI is a technology which depends in part on participation by humans in training and improving the automation potential. We focus on the development of an "AI twin" that could complement its creator's efforts, enabling them to produce higher-quality output in their individual style. However, AI twins could also, over time, replace individual humans. We analyze this trade-off using a principal-agent model in which agents have the opportunity to make investments into training an AI twin…

Real-time adaptive quantum error correction by model-free multi-agent learning
Manuel Guatto, Francesco Preti, Michael Schilling, Tommaso Calarco, Francisco Andr\'es C\'ardenas-L\'opez, Felix Motzoi
https://arxiv.org/abs/2509.03974

Real-time adaptive quantum error correction by model-free multi-agent learning
Can we build efficient Quantum Error Correction (QEC) that adapts on the fly to time-varying noise? In this work we say yes, and show how. We present a two level framework based on Reinforcement Learning (RL) that learns to correct even non-stationary errors from scratch. At the first level we take advantage of model-free Multi-Agent RL (MARL) to automatically discover full QEC cycle -- logical state encoding, stabilizer measurements, and recovery -- without any prior system knowledge, relying …

Random Trajectory Models for Complex Phenomena
Jeffrey D. Picka
https://arxiv.org/abs/2509.06963 https://arxiv.org/pdf/2509.06963

Random Trajectory Models for Complex Phenomena
Many models for complex phenomena use a model for strongly-interacting elements on a small scale to generate larger-scale simulations of some aspects of experimental realizations. These models may be agent-based (as in the case of discrete element method models for granular flow) or based on pattern-forming systems of PDEs (as in models for Raleigh-Bènard convection patterns). Often these models are purely deterministic, producing a single simulation for each set of initial conditions. If obse…

A MILP-Based Solution to Multi-Agent Motion Planning and Collision Avoidance in Constrained Environments
Akshay Jaitly, Jack Cline, Siavash Farzan
https://arxiv.org/abs/2506.21982

A MILP-Based Solution to Multi-Agent Motion Planning and Collision Avoidance in Constrained Environments
We propose a mixed-integer linear program (MILP) for multi-agent motion planning that embeds Polytopic Action-based Motion Planning (PAAMP) into a sequence-then-solve pipeline. Region sequences confine each agent to adjacent convex polytopes, while a big-M hyperplane model enforces inter-agent separation. Collision constraints are applied only to agents sharing or neighboring a region, which reduces binary variables exponentially compared with naive formulations. An L1 path-length-plus-accelera…

ContestTrade: A Multi-Agent Trading System Based on Internal Contest Mechanism
Li Zhao, Rui Sun, Zuoyou Jiang, Bo Yang, Yuxiao Bai, Mengting Chen, Xinyang Wang, Jing Li, Zuo Bai
https://arxiv.org/abs/2508.00554

ContestTrade: A Multi-Agent Trading System Based on Internal Contest Mechanism
In financial trading, large language model (LLM)-based agents demonstrate significant potential. However, the high sensitivity to market noise undermines the performance of LLM-based trading systems. To address this limitation, we propose a novel multi-agent system featuring an internal competitive mechanism inspired by modern corporate management structures. The system consists of two specialized teams: (1) Data Team - responsible for processing and condensing massive market data into diversif…

Astra: A Multi-Agent System for GPU Kernel Performance Optimization
Anjiang Wei, Tianran Sun, Yogesh Seenichamy, Hang Song, Anne Ouyang, Azalia Mirhoseini, Ke Wang, Alex Aiken
https://arxiv.org/abs/2509.07506

Astra: A Multi-Agent System for GPU Kernel Performance Optimization
GPU kernel optimization has long been a central challenge at the intersection of high-performance computing and machine learning. Efficient kernels are crucial for accelerating large language model (LLM) training and serving, yet attaining high performance typically requires extensive manual tuning. Compiler-based systems reduce some of this burden, but still demand substantial manual design and engineering effort. Recently, researchers have explored using LLMs for GPU kernel generation, though…

Multi-Agent Reinforcement Learning for Dynamic Pricing in Supply Chains: Benchmarking Strategic Agent Behaviours under Realistically Simulated Market Conditions
Thomas Hazenberg, Yao Ma, Seyed Sahand Mohammadi Ziabari, Marijn van Rijswijk
https://arxiv.org/abs/2507.02698

Multi-Agent Reinforcement Learning for Dynamic Pricing in Supply Chains: Benchmarking Strategic Agent Behaviours under Realistically Simulated Market Conditions
This study investigates how Multi-Agent Reinforcement Learning (MARL) can improve dynamic pricing strategies in supply chains, particularly in contexts where traditional ERP systems rely on static, rule-based approaches that overlook strategic interactions among market actors. While recent research has applied reinforcement learning to pricing, most implementations remain single-agent and fail to model the interdependent nature of real-world supply chains. This study addresses that gap by evalu…

Model Editing as a Double-Edged Sword: Steering Agent Ethical Behavior Toward Beneficence or Harm
Baixiang Huang, Zhen Tan, Haoran Wang, Zijie Liu, Dawei Li, Ali Payani, Huan Liu, Tianlong Chen, Kai Shu
https://arxiv.org/abs/2506.20606

Model Editing as a Double-Edged Sword: Steering Agent Ethical Behavior Toward Beneficence or Harm
Agents based on Large Language Models (LLMs) have demonstrated strong capabilities across a wide range of tasks. However, deploying LLM-based agents in high-stakes domains comes with significant safety and ethical risks. Unethical behavior by these agents can directly result in serious real-world consequences, including physical harm and financial loss. To efficiently steer the ethical behavior of agents, we frame agent behavior steering as a model editing task, which we term Behavior Editing. …

Gradientsys: A Multi-Agent LLM Scheduler with ReAct Orchestration
Xinyuan Song, Zeyu Wang, Siyi Wu, Tianyu Shi, Lynn Ai
https://arxiv.org/abs/2507.06520 ht…

Gradientsys: A Multi-Agent LLM Scheduler with ReAct Orchestration
We present Gradientsys, a next-generation multi-agent scheduling framework that coordinates diverse specialized AI agents using a typed Model-Context Protocol (MCP) and a ReAct-based dynamic planning loop. At its core, Gradientsys employs an LLM-powered scheduler for intelligent one-to-many task dispatch, enabling parallel execution of heterogeneous agents such as PDF parsers, web search modules, GUI controllers, and web builders. The framework supports hybrid synchronous/asynchronous execution…

Aligning Requirement for Large Language Model's Code Generation
Zhao Tian, Junjie Chen
https://arxiv.org/abs/2509.01313 https://arxiv.org/pdf/2509.0131…

Aligning Requirement for Large Language Model's Code Generation
Code generation refers to the automatic generation of source code based on a given programming specification, which has garnered significant attention particularly with the advancement of large language models (LLMs). However, due to the inherent complexity of real-world problems, the LLM-generated code often fails to fully align with the provided specification. While state-of-the-art agent-based techniques have been proposed to enhance LLM code generation, they overlook the critical issue of s…

From model-based learning to model-free behaviour with Meta-Interpretive Learning
Stassa Patsantzis
https://arxiv.org/abs/2507.16434 https://

From model-based learning to model-free behaviour with Meta-Interpretive Learning
A "model" is a theory that describes the state of an environment and the effects of an agent's decisions on the environment. A model-based agent can use its model to predict the effects of its future actions and so plan ahead, but must know the state of the environment. A model-free agent cannot plan, but can act without a model and without completely observing the environment. An autonomous agent capable of acting independently in novel environments must combine both sets of capabilities. We s…

PhysiBoSS-Models: A database for multiscale models
Vincent Noel, Marco Ruscone, Randy Heiland, Arnau Montagud, Alfonso Valencia, Emmanuel Barillot, Paul Macklin, Laurence Calzone
https://arxiv.org/abs/2508.05550

PhysiBoSS-Models: A database for multiscale models
PhysiBoSS is an open-source platform that integrates agent-based modeling of cell populations with intracellular stochastic Boolean networks, enabling multiscale simulations of complex biological behaviors. To promote model sharing and versioning, we present the PhysiBoSS-Models database: a curated repository for multiscale models built with PhysiBoSS. By providing a simple Python API, PhysiBoSS-Models provides an easy way to download and simulate preexisting models through tools such as PhysiC…

Batched Stochastic Matching Bandits
Jung-hun Kim, Min-hwan Oh
https://arxiv.org/abs/2509.04194 https://arxiv.org/pdf/2509.04194

Batched Stochastic Matching Bandits
In this study, we introduce a novel bandit framework for stochastic matching based on the Multi-nomial Logit (MNL) choice model. In our setting, $N$ agents on one side are assigned to $K$ arms on the other side, where each arm stochastically selects an agent from its assigned pool according to an unknown preference and yields a corresponding reward. The objective is to minimize regret by maximizing the cumulative revenue from successful matches across all agents. This task requires solving a co…

Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS
Bingyu Yan, Ziyi Zhou, Xiaoming Zhang, Chaozhuo Li, Ruilin Zeng, Yirui Qi, Tianbo Wang, Litian Zhang
https://arxiv.org/abs/2508.03125

Attack the Messages, Not the Agents: A Multi-round Adaptive Stealthy Tampering Framework for LLM-MAS
Large language model-based multi-agent systems (LLM-MAS) effectively accomplish complex and dynamic tasks through inter-agent communication, but this reliance introduces substantial safety vulnerabilities. Existing attack methods targeting LLM-MAS either compromise agent internals or rely on direct and overt persuasion, which limit their effectiveness, adaptability, and stealthiness. In this paper, we propose MAST, a Multi-round Adaptive Stealthy Tampering framework designed to exploit communic…

An agent-based model of the power and carbon markets https://www.sciencedirect.com/science/article/pii/S0140988325005158 @…

On Efficient Bayesian Exploration in Model-Based Reinforcement Learning
Alberto Caron, Chris Hicks, Vasilios Mavroudis
https://arxiv.org/abs/2507.02639 htt…

On Efficient Bayesian Exploration in Model-Based Reinforcement Learning
In this work, we address the challenge of data-efficient exploration in reinforcement learning by examining existing principled, information-theoretic approaches to intrinsic motivation. Specifically, we focus on a class of exploration bonuses that targets epistemic uncertainty rather than the aleatoric noise inherent in the environment. We prove that these bonuses naturally signal epistemic information gains and converge to zero once the agent becomes sufficiently certain about the environment…

LLM-based Multi-Agent System for Intelligent Refactoring of Haskell Code
Shahbaz Siddeeq, Muhammad Waseem, Zeeshan Rasheed, Md Mahade Hasan, Jussi Rasku, Mika Saari, Henri Terho, Kalle Makela, Kai-Kristian Kemell, Pekka Abrahamsson
https://arxiv.org/abs/2506.19481

LLM-based Multi-Agent System for Intelligent Refactoring of Haskell Code
Refactoring is a constant activity in software development and maintenance. Scale and maintain software systems are based on code refactoring. However, this process is still labor intensive, as it requires programmers to analyze the codebases in detail to avoid introducing new defects. In this research, we put forward a large language model (LLM)-based multi-agent system to automate the refactoring process on Haskell code. The objective of this research is to evaluate the effect of LLM-based ag…

CREW-WILDFIRE: Benchmarking Agentic Multi-Agent Collaborations at Scale
Jonathan Hyun, Nicholas R Waytowich, Boyuan Chen
https://arxiv.org/abs/2507.05178 h…

CREW-WILDFIRE: Benchmarking Agentic Multi-Agent Collaborations at Scale
Despite rapid progress in large language model (LLM)-based multi-agent systems, current benchmarks fall short in evaluating their scalability, robustness, and coordination capabilities in complex, dynamic, real-world tasks. Existing environments typically focus on small-scale, fully observable, or low-complexity domains, limiting their utility for developing and assessing next-generation multi-agent Agentic AI frameworks. We introduce CREW-Wildfire, an open-source benchmark designed to close th…

Pok\'eAI: A Goal-Generating, Battle-Optimizing Multi-agent System for Pokemon Red
Zihao Liu, Xinhang Sui, Yueran Song, Siwen Wang
https://arxiv.org/abs/2506.23689

PokéAI: A Goal-Generating, Battle-Optimizing Multi-agent System for Pokemon Red
We introduce PokéAI, the first text-based, multi-agent large language model (LLM) framework designed to autonomously play and progress through Pokémon Red. Our system consists of three specialized agents-Planning, Execution, and Critique-each with its own memory bank, role, and skill set. The Planning Agent functions as the central brain, generating tasks to progress through the game. These tasks are then delegated to the Execution Agent, which carries them out within the game environment. Up…

LLM-Based Intelligent Agents for Music Recommendation: A Comparison with Classical Content-Based Filtering
Ronald Carvalho Boadana, Ademir Guimar\~aes da Costa Junior, Ricardo Rios, F\'abio Santos da Silva
https://arxiv.org/abs/2508.11671

LLM-Based Intelligent Agents for Music Recommendation: A Comparison with Classical Content-Based Filtering
The growing availability of music on streaming platforms has led to information overload for users. To address this issue and enhance the user experience, increasingly sophisticated recommendation systems have been proposed. This work investigates the use of Large Language Models (LLMs) from the Gemini and LLaMA families, combined with intelligent agents, in a multi-agent personalized music recommendation system. The results are compared with a traditional content-based recommendation model, co…

Exploring the Stratified Space Structure of an RL Game with the Volume Growth Transform
Justin Curry, Brennan Lagasse, Ngoc B. Lam, Gregory Cox, David Rosenbluth, Alberto Speranzon
https://arxiv.org/abs/2507.22010

Exploring the Stratified Space Structure of an RL Game with the Volume Growth Transform
In this work, we explore the structure of the embedding space of a transformer model trained for playing a particular reinforcement learning (RL) game. Specifically, we investigate how a transformer-based Proximal Policy Optimization (PPO) model embeds visual inputs in a simple environment where an agent must collect "coins" while avoiding dynamic obstacles consisting of "spotlights." By adapting Robinson et al.'s study of the volume growth transform for LLMs to the RL setting, we find that the…

AdamMeme: Adaptively Probe the Reasoning Capacity of Multimodal Large Language Models on Harmfulness
Zixin Chen, Hongzhan Lin, Kaixin Li, Ziyang Luo, Zhen Ye, Guang Chen, Zhiyong Huang, Jing Ma
https://arxiv.org/abs/2507.01702

AdamMeme: Adaptively Probe the Reasoning Capacity of Multimodal Large Language Models on Harmfulness
The proliferation of multimodal memes in the social media era demands that multimodal Large Language Models (mLLMs) effectively understand meme harmfulness. Existing benchmarks for assessing mLLMs on harmful meme understanding rely on accuracy-based, model-agnostic evaluations using static datasets. These benchmarks are limited in their ability to provide up-to-date and thorough assessments, as online memes evolve dynamically. To address this, we propose AdamMeme, a flexible, agent-based evalua…

Agentic Workflow for Education: Concepts and Applications
Yuan-Hao Jiang, Yijie Lu, Ling Dai, Jiatong Wang, Ruijia Li, Bo Jiang
https://arxiv.org/abs/2509.01517 https://

Agentic Workflow for Education: Concepts and Applications
With the rapid advancement of Large Language Models (LLMs) and Artificial Intelligence (AI) agents, agentic workflows are showing transformative potential in education. This study introduces the Agentic Workflow for Education (AWE), a four-component model comprising self-reflection, tool invocation, task planning, and multi-agent collaboration. We distinguish AWE from traditional LLM-based linear interactions and propose a theoretical framework grounded in the von Neumann Multi-Agent System (MA…

A finite element framework for simulating residential burglary in realistic urban geometries
Baoli Hao, Kamrun Mily, Annalisa Quaini, Ming Zhong
https://arxiv.org/abs/2508.11055

A finite element framework for simulating residential burglary in realistic urban geometries
We consider a partial differential equation (PDE) model to predict residential burglary derived from a probabilistic agent-based model through a mean-field limit operation. The PDE model is a nonlinear, coupled system of two equations in two variables (attractiveness of residential sites and density of criminals), similar to the Keller-Segel model for aggregation based on chemotaxis. Unlike previous works, which applied periodic boundary conditions, we enforce boundary conditions that arise nat…

Reinforcement Learning for Automated Cybersecurity Penetration Testing
Daniel L\'opez-Montero, Jos\'e L. \'Alvarez-Aldana, Alicia Morales-Mart\'inez, Marta Gil-L\'opez, Juan M. Au\~n\'on Garc\'ia
https://arxiv.org/abs/2507.02969

Reinforcement Learning for Automated Cybersecurity Penetration Testing
This paper aims to provide an innovative machine learning-based solution to automate security testing tasks for web applications, ensuring the correct functioning of all components while reducing project maintenance costs. Reinforcement Learning is proposed to select and prioritize tools and optimize the testing path. The presented approach utilizes a simulated webpage along with its network topology to train the agent. Additionally, the model leverages Geometric Deep Learning to create priors …

Model Predictive Adversarial Imitation Learning for Planning from Observation
Tyler Han, Yanda Bao, Bhaumik Mehta, Gabriel Guo, Anubhav Vishwakarma, Emily Kang, Sanghun Jung, Rosario Scalise, Jason Zhou, Bryan Xu, Byron Boots
https://arxiv.org/abs/2507.21533

Model Predictive Adversarial Imitation Learning for Planning from Observation
Human demonstration data is often ambiguous and incomplete, motivating imitation learning approaches that also exhibit reliable planning behavior. A common paradigm to perform planning-from-demonstration involves learning a reward function via Inverse Reinforcement Learning (IRL) then deploying this reward via Model Predictive Control (MPC). Towards unifying these methods, we derive a replacement of the policy in IRL with a planning-based agent. With connections to Adversarial Imitation Learnin…

The role of zealots in the spread of linguistic traits
Vivian Dornelas, Celia Anteneodo, Renan Nunes, Els Heinsalu, Marco Patriarca
https://arxiv.org/abs/2508.01500 https://

The role of zealots in the spread of linguistic traits
We investigate the diffusion of linguistic innovations on a fully connected network in order to understand the emergence of linguistic diversity. We employ an agent-based dynamics based on the Axelrod model, where interactions between agents are driven by homophily and social influence, with the difference that we assume that all agents share a number of common features that ensure a finite probability of pairwise interaction. We start from a homogeneous population and introduce zealots that ac…

How do you know if travellers prefer bus, tram or train for a given trip, everything else being equal?
A difficult question. You cannot use a traditional stated preference survey.
With Anne-Valérie Preto, we've differentiated public transport modes in our activity-based, agent-based demand model, #SIMBA #MOBi

LLM Agent for Hyper-Parameter Optimization
Wanzhe Wang, Jianqiu Peng, Menghao Hu, Weihuang Zhong, Tong Zhang, Shuai Wang, Yixin Zhang, Mingjie Shao, Wanli Ni
https://arxiv.org/abs/2506.15167

LLM Agent for Hyper-Parameter Optimization
Hyper-parameters are essential and critical for the performance of communication algorithms. However, current hyper-parameters tuning methods for warm-start particles swarm optimization with cross and mutation (WS-PSO-CM) algortihm for radio map-enabled unmanned aerial vehicle (UAV) trajectory and communication are primarily heuristic-based, exhibiting low levels of automation and unsatisfactory performance. In this paper, we design an large language model (LLM) agent for automatic hyper-parame…

Performance improvement of spatial semantic segmentation with enriched audio features and agent-based error correction for DCASE 2025 Challenge Task 4
Jongyeon Park, Joonhee Lee, Do-Hyeon Lim, Hong Kook Kim, Hyeongcheol Geum, Jeong Eun Lim
https://arxiv.org/abs/2506.21174

Performance improvement of spatial semantic segmentation with enriched audio features and agent-based error correction for DCASE 2025 Challenge Task 4
This technical report presents submission systems for Task 4 of the DCASE 2025 Challenge. This model incorporates additional audio features (spectral roll-off and chroma features) into the embedding feature extracted from the mel-spectral feature to im-prove the classification capabilities of an audio-tagging model in the spatial semantic segmentation of sound scenes (S5) system. This approach is motivated by the fact that mixed audio often contains subtle cues that are difficult to capture wit…

UI-Venus Technical Report: Building High-performance UI Agents with RFT
Zhangxuan Gu, Zhengwen Zeng, Zhenyu Xu, Xingran Zhou, Shuheng Shen, Yunfei Liu, Beitong Zhou, Changhua Meng, Tianyu Xia, Weizhi Chen, Yue Wen, Jingya Dou, Fei Tang, Jinzhen Lin, Yulin Liu, Zhenlin Guo, Yichen Gong, Heng Jia, Changlong Gao, Yuan Guo, Yong Deng, Zhenyu Guo, Liang Chen, Weiqiang Wang

UI-Venus Technical Report: Building High-performance UI Agents with RFT
We present UI-Venus, a native UI agent that takes only screenshots as input based on a multimodal large language model. UI-Venus achieves SOTA performance on both UI grounding and navigation tasks using only several hundred thousand high-quality training samples through reinforcement finetune (RFT) based on Qwen2.5-VL. Specifically, the 7B and 72B variants of UI-Venus obtain 94.1% / 50.8% and 95.3% / 61.9% on the standard grounding benchmarks, i.e., Screenspot-V2 / Pro, surpassing the previous …

AlphaAgents: Large Language Model based Multi-Agents for Equity Portfolio Constructions
Tianjiao Zhao, Jingrao Lyu, Stokes Jones, Harrison Garber, Stefano Pasquali, Dhagash Mehta
https://arxiv.org/abs/2508.11152

AlphaAgents: Large Language Model based Multi-Agents for Equity Portfolio Constructions
The field of artificial intelligence (AI) agents is evolving rapidly, driven by the capabilities of Large Language Models (LLMs) to autonomously perform and refine tasks with human-like efficiency and adaptability. In this context, multi-agent collaboration has emerged as a promising approach, enabling multiple AI agents to work together to solve complex challenges. This study investigates the application of role-based multi-agent systems to support stock selection in equity research and portfo…

Simulating Human Behavior with the Psychological-mechanism Agent: Integrating Feeling, Thought, and Action
Qing Dong, Pengyuan Liu, Dong Yu, Chen Kang
https://arxiv.org/abs/2507.19495

Simulating Human Behavior with the Psychological-mechanism Agent: Integrating Feeling, Thought, and Action
Generative agents have made significant progress in simulating human behavior, but existing frameworks often simplify emotional modeling and focus primarily on specific tasks, limiting the authenticity of the simulation. Our work proposes the Psychological-mechanism Agent (PSYA) framework, based on the Cognitive Triangle (Feeling-Thought-Action), designed to more accurately simulate human behavior. The PSYA consists of three core modules: the Feeling module (using a layer model of affect to sim…

A stochastic agent-based model for simulating tumor-immune dynamics and evaluating therapeutic strategies
Yuhong Zhang, Chenghang Li, Boya Wang, Jinzhi Lei
https://arxiv.org/abs/2508.12297

A stochastic agent-based model for simulating tumor-immune dynamics and evaluating therapeutic strategies
Tumor-immune interactions are central to cancer progression and treatment outcomes. In this study, we present a stochastic agent-based model that integrates cellular heterogeneity, spatial cell-cell interactions, and drug resistance evolution to simulate tumor growth and immune response in a two-dimensional microenvironment. The model captures dynamic behaviors of four major cell types--tumor cells, cytotoxic T lymphocytes, helper T cells, and regulatory T cells--and incorporates key biological…

AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction
Song Wang, Zhen Tan, Zihan Chen, Shuang Zhou, Tianlong Chen, Jundong Li
https://arxiv.org/abs/2506.17784

AnyMAC: Cascading Flexible Multi-Agent Collaboration via Next-Agent Prediction
Recent progress in large language model (LLM)-based multi-agent collaboration highlights the power of structured communication in enabling collective intelligence. However, existing methods largely rely on static or graph-based inter-agent topologies, lacking the potential adaptability and flexibility in communication. In this work, we propose a new framework that rethinks multi-agent coordination through a sequential structure rather than a graph structure, offering a significantly larger topo…

MountainLion: A Multi-Modal LLM-Based Agent System for Interpretable and Adaptive Financial Trading
Siyi Wu, Zhaoyang Guan, Leyi Zhao, Xinyuan Song, Xinyu Ying, Hanlin Zhang, Michele Pak, Yangfan He, Yi Xin, Jianhui Wang, Tianyu Shi
https://arxiv.org/abs/2507.20474

MountainLion: A Multi-Modal LLM-Based Agent System for Interpretable and Adaptive Financial Trading
Cryptocurrency trading is a challenging task requiring the integration of heterogeneous data from multiple modalities. Traditional deep learning and reinforcement learning approaches typically demand large training datasets and encode diverse inputs into numerical representations, often at the cost of interpretability. Recent progress in large language model (LLM)-based agents has demonstrated the capacity to process multi-modal data and support complex investment decision-making. Building on t…

Multi-Agent Coordination under Poisson Observations: A Global Game Approach
Marcos M. Vasconcelos, Behrouz Touri
https://arxiv.org/abs/2507.00424 https://

Multi-Agent Coordination under Poisson Observations: A Global Game Approach
We study a model of strategic coordination based on a class of games with incomplete information known as Global Games. Under the assumption of Poisson-distributed signals and a Gamma prior distribution on state of the system, we demonstrate the existence of a Bayesian Nash equilibrium within the class of threshold policies for utility functions that are linear in the agents' actions. Although computing the exact threshold that constitutes an equilibrium in a system with finitely many agents is…

The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management
Tobias Lindenbauer, Igor Slinko, Ludwig Felder, Egor Bogomolov, Yaroslav Zharov
https://arxiv.org/abs/2508.21433

The Complexity Trap: Simple Observation Masking Is as Efficient as LLM Summarization for Agent Context Management
Large Language Model (LLM)-based agents solve complex tasks through iterative reasoning, exploration, and tool-use, a process that can result in long, expensive context histories. While state-of-the-art Software Engineering ( SE) agents like OpenHands or Cursor use LLM-based summarization to tackle this issue, it is unclear whether the increased complexity offers tangible performance benefits compared to simply omitting older observations. We present a systematic comparison of these strategies …

From CVE Entries to Verifiable Exploits: An Automated Multi-Agent Framework for Reproducing CVEs
Saad Ullah, Praneeth Balasubramanian, Wenbo Guo, Amanda Burnett, Hammond Pearce, Christopher Kruegel, Giovanni Vigna, Gianluca Stringhini
https://arxiv.org/abs/2509.01835

From CVE Entries to Verifiable Exploits: An Automated Multi-Agent Framework for Reproducing CVEs
High-quality datasets of real-world vulnerabilities and their corresponding verifiable exploits are crucial resources in software security research. Yet such resources remain scarce, as their creation demands intensive manual effort and deep security expertise. In this paper, we present CVE-GENIE, an automated, large language model (LLM)-based multi-agent framework designed to reproduce real-world vulnerabilities, provided in Common Vulnerabilities and Exposures (CVE) format, to enable creation…

Replaced article(s) found for q-bio.PE. https://arxiv.org/list/q-bio.PE/new
[1/1]:
- Simulating nationwide coupled disease and fear spread in an agent-based model
Kitson, Alexander, Tuccillo, Butts, Brelsford, Bhatele, Del Valle, Germann

Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent
Chunlong Wu, Zhibo Qu
https://arxiv.org/abs/2509.03990 https://

Meta-Policy Reflexion: Reusable Reflective Memory and Rule Admissibility for Resource-Efficient LLM Agent
Large language model (LLM) agents achieve impressive single-task performance but commonly exhibit repeated failures, inefficient exploration, and limited cross-task adaptability. Existing reflective strategies (e.g., Reflexion, ReAct) improve per-episode behavior but typically produce ephemeral, task-specific traces that are not reused across tasks. Reinforcement-learning based alternatives can produce transferable policies but require substantial parameter updates and compute. In this work we …

Multi-Scale Network Dynamics and Systemic Risk: A Model Context Protocol Approach to Financial Markets
Avishek Bhandari
https://arxiv.org/abs/2507.08065 https://

Multi-Scale Network Dynamics and Systemic Risk: A Model Context Protocol Approach to Financial Markets
This paper introduces a novel framework for analyzing systemic risk in financial markets through multi-scale network dynamics using Model Context Protocol (MCP) for agent communication. We develop an integrated approach that combines transfer entropy networks, agent-based modeling, and wavelet decomposition to capture information flows across temporal scales implemented in the MCPFM (Model Context Protocol Financial Markets) R package. Our methodology enables heterogeneous financial agents incl…

Interpreting the Interpreter: Can We Model post-ECB Conferences Volatility with LLM Agents?
Umberto Collodel
https://arxiv.org/abs/2508.13635 https://arxiv…

Interpreting the Interpreter: Can We Model post-ECB Conferences Volatility with LLM Agents?
This paper develops a novel method to simulate financial market reactions to European Central Bank (ECB) press conferences using a Large Language Model (LLM). We create a behavioral, agent-based simulation of 30 synthetic traders, each with distinct risk preferences, cognitive biases, and interpretive styles. These agents forecast Euro interest rate swap levels at 3-month, 2-year, and 10-year maturities, with the variation across forecasts serving as a measure of market uncertainty or disagreem…

A Late Collaborative Perception Framework for 3D Multi-Object and Multi-Source Association and Fusion
Maryem Fadili (VeDeCom, IRSEEM), Mohamed Anis Ghaoui (VeDeCom), Louis Lecrosnier (IRSEEM, ESIGELEC), Steve Pechberti (VeDeCom), Redouane Khemmar (IRSEEM, ESIGELEC, IRSEEM)
https://arxiv.org/abs/2507.02430

A Late Collaborative Perception Framework for 3D Multi-Object and Multi-Source Association and Fusion
In autonomous driving, recent research has increasingly focused on collaborative perception based on deep learning to overcome the limitations of individual perception systems. Although these methods achieve high accuracy, they rely on high communication bandwidth and require unrestricted access to each agent's object detection model architecture and parameters. These constraints pose challenges real-world autonomous driving scenarios, where communication limitations and the need to safeguard p…

LLM-Based Social Simulations Require a Boundary
Zengqing Wu, Run Peng, Takayuki Ito, Chuan Xiao
https://arxiv.org/abs/2506.19806 https://

LLM-Based Social Simulations Require a Boundary
This position paper argues that large language model (LLM)-based social simulations should establish clear boundaries to meaningfully contribute to social science research. While LLMs offer promising capabilities for modeling human-like agents compared to traditional agent-based modeling, they face fundamental limitations that constrain their reliability for social pattern discovery. The core issue lies in LLMs' tendency towards an ``average persona'' that lacks sufficient behavioral heterogene…

The Multi-Agent Fault Localization System Based on Monte Carlo Tree Search Approach
Rui Ren
https://arxiv.org/abs/2507.22800 https://arxiv.org/pdf/2507.228…

The Multi-Agent Fault Localization System Based on Monte Carlo Tree Search Approach
In real-world scenarios, due to the highly decoupled and flexible nature of microservices, it poses greater challenges to system reliability. The more frequent occurrence of incidents has created a demand for Root Cause Analysis(RCA) methods that enable rapid identification and recovery of incidents. Large language model (LLM) provides a new path for quickly locating and recovering from incidents by leveraging their powerful generalization ability combined with expert experience. Current LLM fo…

MLC-Agent: Cognitive Model based on Memory-Learning Collaboration in LLM Empowered Agent Simulation Environment
Ming Zhang, Yiling Xuan, Qun Ma, Yuwei Guo
https://arxiv.org/abs/2507.20215

MLC-Agent: Cognitive Model based on Memory-Learning Collaboration in LLM Empowered Agent Simulation Environment
Many real-world systems, such as transportation systems, ecological systems, and Internet systems, are complex systems. As an important tool for studying complex systems, computational experiments can map them into artificial society models that are computable and reproducible within computers, thereby providing digital and computational methods for quantitative analysis. In current research, the construction of individual agent models often ignores the long-term accumulative effect of memory m…

Toward the Autonomous AI Doctor: Quantitative Benchmarking of an Autonomous Agentic AI Versus Board-Certified Clinicians in a Real World Setting
Hashim Hayat, Maksim Kudrautsau, Evgeniy Makarov, Vlad Melnichenko, Tim Tsykunou, Piotr Varaksin, Matt Pavelle, Adam Z. Oskowitz
https://arxiv.org/abs/2507.22902

Toward the Autonomous AI Doctor: Quantitative Benchmarking of an Autonomous Agentic AI Versus Board-Certified Clinicians in a Real World Setting
Background: Globally we face a projected shortage of 11 million healthcare practitioners by 2030, and administrative burden consumes 50% of clinical time. Artificial intelligence (AI) has the potential to help alleviate these problems. However, no end-to-end autonomous large language model (LLM)-based AI system has been rigorously evaluated in real-world clinical practice. In this study, we evaluated whether a multi-agent LLM-based AI framework can function autonomously as an AI doctor in a vir…

Dynamic Speculative Agent Planning
Yilin Guan, Wenyue Hua, Qingfeng Lan, Sun Fei, Dujian Ding, Devang Acharya, Chi Wang, William Yang Wang
https://arxiv.org/abs/2509.01920 https…

Dynamic Speculative Agent Planning
Despite their remarkable success in complex tasks propelling widespread adoption, large language-model-based agents still face critical deployment challenges due to prohibitive latency and inference costs. While recent work has explored various methods to accelerate inference, existing approaches suffer from significant limitations: they either fail to preserve performance fidelity, require extensive offline training of router modules, or incur excessive operational costs. Moreover, they provid…

Value-Based Large Language Model Agent Simulation for Mutual Evaluation of Trust and Interpersonal Closeness
Yuki Sakamoto, Takahisa Uchida, Hiroshi Ishiguro
https://arxiv.org/abs/2507.11979

Value-Based Large Language Model Agent Simulation for Mutual Evaluation of Trust and Interpersonal Closeness
Large language models (LLMs) have emerged as powerful tools for simulating complex social phenomena using human-like agents with specific traits. In human societies, value similarity is important for building trust and close relationships; however, it remains unexplored whether this principle holds true in artificial societies comprising LLM agents. Therefore, this study investigates the influence of value similarity on relationship-building among LLM agents through two experiments. First, in a…

ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendation
Reza Yousefi Maragheh, Pratheek Vadla, Priyank Gupta, Kai Zhao, Aysenur Inan, Kehui Yao, Jianpeng Xu, Praveen Kanumala, Jason Cho, Sushant Kumar
https://arxiv.org/abs/2506.21931

ARAG: Agentic Retrieval Augmented Generation for Personalized Recommendation
Retrieval-Augmented Generation (RAG) has shown promise in enhancing recommendation systems by incorporating external context into large language model prompts. However, existing RAG-based approaches often rely on static retrieval heuristics and fail to capture nuanced user preferences in dynamic recommendation scenarios. In this work, we introduce ARAG, an Agentic Retrieval-Augmented Generation framework for Personalized Recommendation, which integrates a multi-agent collaboration mechanism int…

Trusted Data Fusion, Multi-Agent Autonomy, Autonomous Vehicles
R. Spencer Hallyburton, Miroslav Pajic
https://arxiv.org/abs/2507.17875 https://arxiv.org/pd…

Trusted Data Fusion, Multi-Agent Autonomy, Autonomous Vehicles
Multi-agent collaboration enhances situational awareness in intelligence, surveillance, and reconnaissance (ISR) missions. Ad hoc networks of unmanned aerial vehicles (UAVs) allow for real-time data sharing, but they face security challenges due to their decentralized nature, making them vulnerable to cyber-physical attacks. This paper introduces a trust-based framework for assured sensor fusion in distributed multi-agent networks, utilizing a hidden Markov model (HMM)-based approach to estimat…

Barriers to Healthcare: Agent-Based Modeling to Mitigate Inequity
Alba Aguilera, Georgina Curto, Nardine Osman
https://arxiv.org/abs/2507.23644 https://arx…

Barriers to Healthcare: Agent-Based Modeling to Mitigate Inequity
Agent-based simulations have an enormous potential as tools to evaluate social policies in a non-invasive way, before these are implemented to real-world populations. However, the recommendations that these computational approaches may offer to tackle urgent human development challenges can vary substantially depending on how we model agents' (people) behaviour and the criteria that we use to measure inequity. In this paper, we integrate the conceptual framework of the capability approach (CA),…

Echoes of the Land: An Interactive Installation Based on Physical Model of Earthquake
Ivan C. H. Liu, Chung-En Hao, Jing Xie
https://arxiv.org/abs/2507.14947

Echoes of the Land: An Interactive Installation Based on Physical Model of Earthquake
Echoes of the Land is an interactive installation that transforms seismic dynamics into a multisensory experience through a scientifically grounded spring-block model. Simulating earthquake recurrence and self-organized criticality, the work generates real-time sound and light via motion capture and concatenative granular synthesis. Each block acts as an agent, producing emergent audiovisual cascades that visualize the physics of rupture and threshold behavior. This work exemplifies the amalgam…

When Networks Mislead: How Partisan Communication Undermines Democratic Decision-Making
Hsuan-Wei Lee, Po-Kang Hsiao
https://arxiv.org/abs/2506.21820 https…

When Networks Mislead: How Partisan Communication Undermines Democratic Decision-Making
Democratic societies increasingly rely on communication networks to aggregate citizen preferences and information, yet these same networks can systematically mislead voters under certain conditions. We introduce an agent-based model that captures two rival forces in partisan networks: honest noise filtering that lifts accuracy and strategic bluffing that embeds bias. Extensive simulations show that communication architecture shapes voting accuracy more than any individual-level trait. When cand…

QAgent: An LLM-based Multi-Agent System for Autonomous OpenQASM programming
Zhenxiao Fu, Fan Chen, Lei Jiang
https://arxiv.org/abs/2508.20134 https://arxiv…

QAgent: An LLM-based Multi-Agent System for Autonomous OpenQASM programming
Noisy Intermediate-Scale Quantum (NISQ) devices have begun to exhibit early quantum advantages on classically intractable problems, spanning physics simulations to Gaussian boson sampling. Yet, realizing these benefits remains challenging for non-experts, primarily due to the complexities of programming in Open Quantum Assembly Language (OpenQASM). Although Large Language Model (LLM)-based agents have shown promise in automating classical programming workflows, their quantum counterparts have l…

SimInterview: Transforming Business Education through Large Language Model-Based Simulated Multilingual Interview Training System
Truong Thanh Hung Nguyen, Tran Diem Quynh Nguyen, Hoang Loc Cao, Thi Cam Thanh Tran, Thi Cam Mai Truong, Hung Cao
https://arxiv.org/abs/2508.11873

SimInterview: Transforming Business Education through Large Language Model-Based Simulated Multilingual Interview Training System
Business interview preparation demands both solid theoretical grounding and refined soft skills, yet conventional classroom methods rarely deliver the individualized, culturally aware practice employers currently expect. This paper introduces SimInterview, a large language model (LLM)-based simulated multilingual interview training system designed for business professionals entering the AI-transformed labor market. Our system leverages an LLM agent and synthetic AI technologies to create realis…

Servant, Stalker, Predator: How An Honest, Helpful, And Harmless (3H) Agent Unlocks Adversarial Skills
David Noever
https://arxiv.org/abs/2508.19500 https://

Servant, Stalker, Predator: How An Honest, Helpful, And Harmless (3H) Agent Unlocks Adversarial Skills
This paper identifies and analyzes a novel vulnerability class in Model Context Protocol (MCP) based agent systems. The attack chain describes and demonstrates how benign, individually authorized tasks can be orchestrated to produce harmful emergent behaviors. Through systematic analysis using the MITRE ATLAS framework, we demonstrate how 95 agents tested with access to multiple services-including browser automation, financial analysis, location tracking, and code deployment-can chain legitimat…

Computing Tree Structures in Anonymous Graphs via Mobile Agents
Prabhat Kumar Chand, Manish Kumar, Anisur Rahaman Molla
https://arxiv.org/abs/2506.19365 ht…

Computing Tree Structures in Anonymous Graphs via Mobile Agents
Minimum Spanning Tree (MST) and Breadth-First Search (BFS) tree constructions are classical problems in distributed computing, traditionally studied in the message-passing model, where static nodes communicate via messages. This paper investigates MST and BFS tree construction in an agent-based network, where mobile agents explore a graph and compute. Each node hosts one agent, and communication occurs when agents meet at a node. We consider $n$ agents initially dispersed (one per node) in an a…

Misspecified Bayesianism
Pooya Molavi
https://arxiv.org/abs/2507.22775 https://arxiv.org/pdf/2507.22775

Misspecified Bayesianism
An agent is a misspecified Bayesian if she updates her belief using Bayes' rule given a subjective, possibly misspecified model of her signals. This paper shows that a belief sequence is consistent with misspecified Bayesianism if the prior contains a grain of the average posterior, i.e., is a mixture of the average posterior and another distribution. A partition-based variant of the grain condition is both necessary and sufficient. Under correct specification, the grain condition reduces to th…

Forgive and Forget? An Industry 5.0 Approach to Trust-Fatigue Co-regulation in Human-Cobot Order Picking
Soumyadeep Dhar
https://arxiv.org/abs/2508.03765 https://

Forgive and Forget? An Industry 5.0 Approach to Trust-Fatigue Co-regulation in Human-Cobot Order Picking
This paper investigates the critical role of trust and fatigue in human-cobot collaborative order picking, framing the challenge within the scope of Logistics 5.0 -- the implementation of human-robot symbiosis in smart logistics. We propose a dynamic, leader-follower Stackelberg game to model this interaction, where utility functions explicitly account for human fatigue and trust. Through agent-based simulations, we demonstrate that while a naive model leads to a "trust death spiral," a refined…

Analyzing Information Sharing and Coordination in Multi-Agent Planning
Tianyue Ou, Saujas Vaduguru, Daniel Fried
https://arxiv.org/abs/2508.12981 https://a…

Analyzing Information Sharing and Coordination in Multi-Agent Planning
Multi-agent systems (MASs) have pushed the boundaries of large language model (LLM) agents in domains such as web research and software engineering. However, long-horizon, multi-constraint planning tasks involve conditioning on detailed information and satisfying complex interdependent constraints, which can pose a challenge for these systems. In this study, we construct an LLM-based MAS for a travel planning task which is representative of these challenges. We evaluate the impact of a notebook…

A Concurrent Modular Agent: Framework for Autonomous LLM Agents
Norihiro Maruyama, Takahide Yoshida, Hiroki Sato, Atsushi Masumori, Johnsmith, Takashi Ikegami
https://arxiv.org/abs/2508.19042

A Concurrent Modular Agent: Framework for Autonomous LLM Agents
We introduce the Concurrent Modular Agent (CMA), a framework that orchestrates multiple Large-Language-Model (LLM)-based modules that operate fully asynchronously yet maintain a coherent and fault-tolerant behavioral loop. This framework addresses long-standing difficulties in agent architectures by letting intention emerge from language-mediated interactions among autonomous processes. This approach enables flexible, adaptive, and context-dependent behavior through the combination of concurren…

FACET:Teacher-Centred LLM-Based Multi-Agent Systems-Towards Personalized Educational Worksheets
Jana Gonnermann-M\"uller, Jennifer Haase, Konstantin Fackeldey, Sebastian Pokutta
https://arxiv.org/abs/2508.11401

FACET:Teacher-Centred LLM-Based Multi-Agent Systems-Towards Personalized Educational Worksheets
The increasing heterogeneity of student populations poses significant challenges for teachers, particularly in mathematics education, where cognitive, motivational, and emotional differences strongly influence learning outcomes. While AI-driven personalization tools have emerged, most remain performance-focused, offering limited support for teachers and neglecting broader pedagogical needs. This paper presents the FACET framework, a teacher-facing, large language model (LLM)-based multi-agent s…

Emergent collective dynamics from motile photokinetic organisms
J. Morales, P. Munoz, D. Noto, H. N Ulloa, F. Guzman-Lastra
https://arxiv.org/abs/2506.19081

Emergent collective dynamics from motile photokinetic organisms
The day-night cycle drives the largest biomass migration on Earth: the diel vertical migration (DVM) of aquatic organisms. Here, we present a three-dimensional agent-based model that incorporates photokinesis, gyrotaxis, and stochastic reorientation to explore how individual-level swimming behaviors give rise to population-scale DVM patterns. By solving Langevin equations for swarms of swimmers, we identify four distinct regimes -- Surface Accumulation, Shallow DVM, Deep DVM, and Sinking -- gov…

Strategic Communication and Language Bias in Multi-Agent LLM Coordination
Alessio Buscemi, Daniele Proverbio, Alessandro Di Stefano, The Anh Han, German Castignani, Pietro Li\`o
https://arxiv.org/abs/2508.00032

Strategic Communication and Language Bias in Multi-Agent LLM Coordination
Large Language Model (LLM)-based agents are increasingly deployed in multi-agent scenarios where coordination is crucial but not always assured. Previous studies indicate that the language used to frame strategic scenarios can influence cooperative behavior. This paper explores whether allowing agents to communicate amplifies these language-driven effects. Leveraging the FAIRGAME framework, we simulate one-shot and repeated games across different languages and models, both with and without comm…

A Large Language Model-based Multi-Agent Framework for Analog Circuits' Sizing Relationships Extraction
Chengjie Liu, Weiyu Chen, Huiyao Xu, Yuan Du, Jun Yang, Li Du
https://arxiv.org/abs/2506.18424

A Large Language Model-based Multi-Agent Framework for Analog Circuits' Sizing Relationships Extraction
In the design process of the analog circuit pre-layout phase, device sizing is an important step in determining whether an analog circuit can meet the required performance metrics. Many existing techniques extract the circuit sizing task as a mathematical optimization problem to solve and continuously improve the optimization efficiency from a mathematical perspective. But they ignore the automatic introduction of prior knowledge, fail to achieve effective pruning of the search space, which the…

Towards an ABM on Proactive Community Adaptation for Climate Change
\"Onder G\"urcan, David Eric John Herbert, F. LeRon Shults, Christopher Frantz, Ivan Puga-Gonzalez
https://arxiv.org/abs/2507.14233

Towards an ABM on Proactive Community Adaptation for Climate Change
We present an agent-based model (ABM) simulating proactive community adaptation to climate change in an urban context. The model is applied to Bergen, Norway, represented as a complex socio-ecological system. It integrates multiple agent types: municipal government (urban planners and political actors), civil society (individual citizens), environmental NGOs and activists, and media. Agents interact during urban planning processes - particularly the evaluation and approval of new development pr…

Dr.Copilot: A Multi-Agent Prompt Optimized Assistant for Improving Patient-Doctor Communication in Romanian
Andrei Niculae, Adrian Cosma, Cosmin Dumitrache, Emilian R\v{a}doi
https://arxiv.org/abs/2507.11299

Dr.Copilot: A Multi-Agent Prompt Optimized Assistant for Improving Patient-Doctor Communication in Romanian
Text-based telemedicine has become increasingly common, yet the quality of medical advice in doctor-patient interactions is often judged more on how advice is communicated rather than its clinical accuracy. To address this, we introduce Dr.Copilot , a multi-agent large language model (LLM) system that supports Romanian-speaking doctors by evaluating and enhancing the presentation quality of their written responses. Rather than assessing medical correctness, Dr.Copilot provides feedback along 17…

Memory as a Service (MaaS): Rethinking Contextual Memory as Service-Oriented Modules for Collaborative Agents
Haichang Li
https://arxiv.org/abs/2506.22815 …

Memory as a Service (MaaS): Rethinking Contextual Memory as Service-Oriented Modules for Collaborative Agents
This position paper aims to rethink the role and design of memory in Large Language Model (LLM)-based agent systems. We observe that while current memory practices have begun to transcend the limitations of single interactions, they remain conceptually grounded in "bound memory" in terms of design concept-where memory is treated as local state attached to specific context or entities, forming "memory silos" that impede cross-entity collaboration. To overcome this architectural bottleneck, this …

Replicating the behaviour of electric vehicle drivers using an agent-based reinforcement learning model
Zixin Feng, Qunshan Zhao, Alison Heppenstall
https://arxiv.org/abs/2507.21341

Replicating the behaviour of electric vehicle drivers using an agent-based reinforcement learning model
Despite the rapid expansion of electric vehicle (EV) charging networks, questions remain about their efficiency in meeting the growing needs of EV drivers. Previous simulation-based approaches, which rely on static behavioural rules, have struggled to capture the adaptive behaviours of human drivers. Although reinforcement learning has been introduced in EV simulation studies, its application has primarily focused on optimising fleet operations rather than modelling private drivers who make ind…

STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning
Chenghao Wu, Ruiyang Ren, Junjie Zhang, Ruirui Wang, Zhongrui Ma, Qi Ye, Wayne Xin Zhao
https://arxiv.org/abs/2508.18812

STARec: An Efficient Agent Framework for Recommender Systems via Autonomous Deliberate Reasoning
While modern recommender systems are instrumental in navigating information abundance, they remain fundamentally limited by static user modeling and reactive decision-making paradigms. Current large language model (LLM)-based agents inherit these shortcomings through their overreliance on heuristic pattern matching, yielding recommendations prone to shallow correlation bias, limited causal inference, and brittleness in sparse-data scenarios. We introduce STARec, a slow-thinking augmented agent …

Investigating the Potential of Large Language Model-Based Router Multi-Agent Architectures for Foundation Design Automation: A Task Classification and Expert Selection Study
Sompote Youwai, David Phim, Vianne Gayl Murcia, Rianne Clair Onas
https://arxiv.org/abs/2506.13811

Investigating the Potential of Large Language Model-Based Router Multi-Agent Architectures for Foundation Design Automation: A Task Classification and Expert Selection Study
This study investigates router-based multi-agent systems for automating foundation design calculations through intelligent task classification and expert selection. Three approaches were evaluated: single-agent processing, multi-agent designer-checker architecture, and router-based expert selection. Performance assessment utilized baseline models including DeepSeek R1, ChatGPT 4 Turbo, Grok 3, and Gemini 2.5 Pro across shallow foundation and pile design scenarios. The router-based configuration…

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents
Hengyu An, Jinghuai Zhang, Tianyu Du, Chunyi Zhou, Qingming Li, Tao Lin, Shouling Ji
https://arxiv.org/abs/2508.15310

IPIGuard: A Novel Tool Dependency Graph-Based Defense Against Indirect Prompt Injection in LLM Agents
Large language model (LLM) agents are widely deployed in real-world applications, where they leverage tools to retrieve and manipulate external data for complex tasks. However, when interacting with untrusted data sources (e.g., fetching information from public websites), tool responses may contain injected instructions that covertly influence agent behaviors and lead to malicious outcomes, a threat referred to as Indirect Prompt Injection (IPI). Existing defenses typically rely on advanced pro…

Code Researcher: Deep Research Agent for Large Systems Code and Commit History
Ramneet Singh, Sathvik Joel, Abhav Mehrotra, Nalin Wadhwa, Ramakrishna B Bairi, Aditya Kanade, Nagarajan Natarajan
https://arxiv.org/abs/2506.11060

Code Researcher: Deep Research Agent for Large Systems Code and Commit History
Large Language Model (LLM)-based coding agents have shown promising results on coding benchmarks, but their effectiveness on systems code remains underexplored. Due to the size and complexities of systems code, making changes to a systems codebase is a daunting task, even for humans. It requires researching about many pieces of context, derived from the large codebase and its massive commit history, before making changes. Inspired by the recent progress on deep research agents, we design the fi…

Tactical Decision for Multi-UGV Confrontation with a Vision-Language Model-Based Commander
Li Wang, Qizhen Wu, Lei Chen
https://arxiv.org/abs/2507.11079 ht…

Tactical Decision for Multi-UGV Confrontation with a Vision-Language Model-Based Commander
In multiple unmanned ground vehicle confrontations, autonomously evolving multi-agent tactical decisions from situational awareness remain a significant challenge. Traditional handcraft rule-based methods become vulnerable in the complicated and transient battlefield environment, and current reinforcement learning methods mainly focus on action manipulation instead of strategic decisions due to lack of interpretability. Here, we propose a vision-language model-based commander to address the iss…

Mind the Gap: Time-of-Check to Time-of-Use Vulnerabilities in LLM-Enabled Agents
Derek Lilienthal, Sanghyun Hong
https://arxiv.org/abs/2508.17155 https://a…

Mind the Gap: Time-of-Check to Time-of-Use Vulnerabilities in LLM-Enabled Agents
Large Language Model (LLM)-enabled agents are rapidly emerging across a wide range of applications, but their deployment introduces vulnerabilities with security implications. While prior work has examined prompt-based attacks (e.g., prompt injection) and data-oriented threats (e.g., data exfiltration), time-of-check to time-of-use (TOCTOU) remain largely unexplored in this context. TOCTOU arises when an agent validates external state (e.g., a file or API response) that is later modified before…

Voice-based AI Agents: Filling the Economic Gaps in Digital Health Delivery
Bo Wen, Chen Wang, Qiwei Han, Raquel Norel, Julia Liu, Thaddeus Stappenbeck, Jeffrey L. Rogers
https://arxiv.org/abs/2507.16229

Voice-based AI Agents: Filling the Economic Gaps in Digital Health Delivery
The integration of voice-based AI agents in healthcare presents a transformative opportunity to bridge economic and accessibility gaps in digital health delivery. This paper explores the role of large language model (LLM)-powered voice assistants in enhancing preventive care and continuous patient monitoring, particularly in underserved populations. Drawing insights from the development and pilot study of Agent PULSE (Patient Understanding and Liaison Support Engine) -- a collaborative initiati…

Towards Simulating Social Influence Dynamics with LLM-based Multi-agents
Hsien-Tsung Lin, Pei-Cing Huang, Chan-Tung Ku, Chan Hsu, Pei-Xuan Shieh, Yihuang Kang
https://arxiv.org/abs/2507.22467

Towards Simulating Social Influence Dynamics with LLM-based Multi-agents
Recent advancements in Large Language Models offer promising capabilities to simulate complex human social interactions. We investigate whether LLM-based multi-agent simulations can reproduce core human social dynamics observed in online forums. We evaluate conformity dynamics, group polarization, and fragmentation across different model scales and reasoning capabilities using a structured simulation framework. Our findings indicate that smaller models exhibit higher conformity rates, whereas m…

Uncertainty-Aware Knowledge Transformers for Peer-to-Peer Energy Trading with Multi-Agent Reinforcement Learning
Mian Ibad Ali Shah, Enda Barrett, Karl Mason
https://arxiv.org/abs/2507.16796

Uncertainty-Aware Knowledge Transformers for Peer-to-Peer Energy Trading with Multi-Agent Reinforcement Learning
This paper presents a novel framework for Peer-to-Peer (P2P) energy trading that integrates uncertainty-aware prediction with multi-agent reinforcement learning (MARL), addressing a critical gap in current literature. In contrast to previous works relying on deterministic forecasts, the proposed approach employs a heteroscedastic probabilistic transformer-based prediction model called Knowledge Transformer with Uncertainty (KTU) to explicitly quantify prediction uncertainty, which is essential …

Bayesian Optimization-based Search for Agent Control in Automated Game Testing
Carlos Celemin
https://arxiv.org/abs/2508.13121 https://arxiv.org/pdf/2508.1…

Bayesian Optimization-based Search for Agent Control in Automated Game Testing
This work introduces an automated testing approach that employs agents controlling game characters to detect potential bugs within a game level. Harnessing the power of Bayesian Optimization (BO) to execute sample-efficient search, the method determines the next sampling point by analyzing the data collected so far and calculates the data point that will maximize information acquisition. To support the BO process, we introduce a game testing-specific model built on top of a grid map, that featu…

ShortageSim: Simulating Drug Shortages under Information Asymmetry
Mingxuan Cui, Yilan Jiang, Duo Zhou, Cheng Qian, Yuji Zhang, Qiong Wang
https://arxiv.org/abs/2509.01813 https…

ShortageSim: Simulating Drug Shortages under Information Asymmetry
Drug shortages pose critical risks to patient care and healthcare systems worldwide, yet the effectiveness of regulatory interventions remains poorly understood due to fundamental information asymmetries in pharmaceutical supply chains. We present \textbf{ShortageSim}, the first Large Language Model (LLM)-based multi-agent simulation framework that captures the complex, strategic interactions between drug manufacturers, institutional buyers, and regulatory agencies in response to shortage alert…

Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems
Yutong Wu, Jie Zhang, Yiming Li, Chao Zhang, Qing Guo, Nils Lukas, Tianwei Zhang
https://arxiv.org/abs/2508.09230 h…

Cowpox: Towards the Immunity of VLM-based Multi-Agent Systems
Vision Language Model (VLM)-based agents are stateful, autonomous entities capable of perceiving and interacting with their environments through vision and language. Multi-agent systems comprise specialized agents who collaborate to solve a (complex) task. A core security property is robustness, stating that the system should maintain its integrity under adversarial attacks. However, the design of existing multi-agent systems lacks the robustness consideration, as a successful exploit against o…

Lessons Learned from Evaluation of LLM based Multi-agents in Safer Therapy Recommendation
Yicong Wu, Ting Chen, Irit Hochberg, Zhoujian Sun, Ruth Edry, Zhengxing Huang, Mor Peleg
https://arxiv.org/abs/2507.10911

Lessons Learned from Evaluation of LLM based Multi-agents in Safer Therapy Recommendation
Therapy recommendation for chronic patients with multimorbidity is challenging due to risks of treatment conflicts. Existing decision support systems face scalability limitations. Inspired by the way in which general practitioners (GP) manage multimorbidity patients, occasionally convening multidisciplinary team (MDT) collaboration, this study investigated the feasibility and value of using a Large Language Model (LLM)-based multi-agent system (MAS) for safer therapy recommendations. We designe…

Instructional Agents: LLM Agents on Automated Course Material Generation for Teaching Faculties
Huaiyuan Yao, Wanpeng Xu, Justin Turnau, Nadia Kellam, Hua Wei
https://arxiv.org/abs/2508.19611

Instructional Agents: LLM Agents on Automated Course Material Generation for Teaching Faculties
Preparing high-quality instructional materials remains a labor-intensive process that often requires extensive coordination among teaching faculty, instructional designers, and teaching assistants. In this work, we present Instructional Agents, a multi-agent large language model (LLM) framework designed to automate end-to-end course material generation, including syllabus creation, lecture scripts, LaTeX-based slides, and assessments. Unlike existing AI-assisted educational tools that focus on …

Shapley Machine: A Game-Theoretic Framework for N-Agent Ad Hoc Teamwork
Jianhong Wang, Yang Li, Samuel Kaski, Jonathan Lawry
https://arxiv.org/abs/2506.11285

Shapley Machine: A Game-Theoretic Framework for N-Agent Ad Hoc Teamwork
Open multi-agent systems are increasingly important in modeling real-world applications, such as smart grids, swarm robotics, etc. In this paper, we aim to investigate a recently proposed problem for open multi-agent systems, referred to as n-agent ad hoc teamwork (NAHT), where only a number of agents are controlled. Existing methods tend to be based on heuristic design and consequently lack theoretical rigor and ambiguous credit assignment among agents. To address these limitations, we model a…

Advanced For-Loop for QML algorithm search
FuTe Wong
https://arxiv.org/abs/2506.18260 https://arxiv.org/pdf/2506.18260

Advanced For-Loop for QML algorithm search
This paper introduces an advanced framework leveraging Large Language Model-based Multi-Agent Systems (LLMMA) for the automated search and optimization of Quantum Machine Learning (QML) algorithms. Inspired by Google DeepMind's FunSearch, the proposed system works on abstract level to iteratively generates and refines quantum transformations of classical machine learning algorithms (concepts), such as the Multi-Layer Perceptron, forward-forward and backpropagation algorithms. As a proof of conc…

KompeteAI: Accelerated Autonomous Multi-Agent System for End-to-End Pipeline Generation for Machine Learning Problems
Stepan Kulibaba, Artem Dzhalilov, Roman Pakhomov, Oleg Svidchenko, Alexander Gasnikov, Aleksei Shpilman
https://arxiv.org/abs/2508.10177

KompeteAI: Accelerated Autonomous Multi-Agent System for End-to-End Pipeline Generation for Machine Learning Problems
Recent Large Language Model (LLM)-based AutoML systems demonstrate impressive capabilities but face significant limitations such as constrained exploration strategies and a severe execution bottleneck. Exploration is hindered by one-shot methods lacking diversity and Monte Carlo Tree Search (MCTS) approaches that fail to recombine strong partial solutions. The execution bottleneck arises from lengthy code validation cycles that stifle iterative refinement. To overcome these challenges, we intro…

Reasoning About Knowledge on Regular Expressions is 2EXPTIME-complete
Avijeet Ghosh, Sujata Ghosh, Fran\c{c}ois Schwarzentruber
https://arxiv.org/abs/2508.09784 https://

Reasoning About Knowledge on Regular Expressions is 2EXPTIME-complete
Logics for reasoning about knowledge and actions have seen many applications in various domains of multi-agent systems, including epistemic planning. Change of knowledge based on observations about the surroundings forms a key aspect in such planning scenarios. Public Observation Logic (POL) is a variant of public announcement logic for reasoning about knowledge that gets updated based on public observations. Each state in an epistemic (Kripke) model is equipped with a set of expected observati…